Spacetimegpt

🚀 SpaceTimeGPT - Video Captioning Model

SpaceTimeGPT is a video description generation model that can perform spatial and temporal reasoning. It samples and analyzes eight frames from a given video, then uses autoregression to generate a sentence describing the events in the video.

📚 Documentation

Dataset

• HuggingFaceM4/vatex

Language

• English

Metrics

• BLEU
• METEOR
• ROUGE

Pipeline Tag

• Video-text-to-text

Inference

• Enabled

Tags

• Video-captioning

Model Index

✨ Features

Architecture and Training

• Vision Encoder: timesformer-base-finetuned-k600
• Text Decoder: gpt2

The encoder and decoder are initialized with pretrained weights for video classification and sentence completion respectively. Encoder-decoder cross attention is used to integrate the visual and linguistic domains. The model is fine-tuned end-to-end for the video captioning task. For more details, please refer to the GitHub repository.

💻 Usage Examples

Basic Usage

import av
import numpy as np
import torch
from transformers import AutoImageProcessor, AutoTokenizer, VisionEncoderDecoderModel

device = "cuda" if torch.cuda.is_available() else "cpu"

# load pretrained processor, tokenizer, and model
image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base")
tokenizer = AutoTokenizer.from_pretrained("gpt2")
model = VisionEncoderDecoderModel.from_pretrained("Neleac/timesformer-gpt2-video-captioning").to(device)

# load video
video_path = "never_gonna_give_you_up.mp4"
container = av.open(video_path)

# extract evenly spaced frames from video
seg_len = container.streams.video[0].frames
clip_len = model.config.encoder.num_frames
indices = set(np.linspace(0, seg_len, num=clip_len, endpoint=False).astype(np.int64))
frames = []
container.seek(0)
for i, frame in enumerate(container.decode(video=0)):
    if i in indices:
        frames.append(frame.to_ndarray(format="rgb24"))

# generate caption
gen_kwargs = {
    "min_length": 10, 
    "max_length": 20, 
    "num_beams": 8,
}
pixel_values = image_processor(frames, return_tensors="pt").pixel_values.to(device)
tokens = model.generate(pixel_values, **gen_kwargs)
caption = tokenizer.batch_decode(tokens, skip_special_tokens=True)[0]
print(caption) # A man and a woman are dancing on a stage in front of a mirror.

👨‍💻 Author Information

• 👾 Discord
• 🐙 GitHub
• 🤝 LinkedIn